© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104166
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amina
    -0.06
    opal
    -0.06
    oro
    -0.06
    algo
    -0.06
    ear
    -0.06
    alink
    -0.06
    443
    -0.06
    iores
    -0.06
     Gupta
    -0.05
     Sad
    -0.05
    POSITIVE LOGITS
    çĽ
    0.07
    ãĥ£
    0.07
    OffsetTable
    0.06
    WebResponse
    0.06
    .BorderFactory
    0.06
    हर
    0.06
    æĿ
    0.06
    ãĥ¼ãĥĭ
    0.06
    æijĩ
    0.06
    acÃŃ
    0.06
    Activations Density 0.000%

    No Known Activations